Trained CatBoost models can be exported to CoreML.

The following example showcases how to train a model using CatBoostClassifier, save it CoreML using the save_model function and import the model to Xcode:

  1. Train the model and save it in CoreML format.

    For example, if training on the Iris dataset:

    import catboost
    import sklearn
    iris = sklearn.datasets.load_iris()
    cls = catboost.CatBoostClassifier(loss_function='MultiClass'),
    # Save model to catboost format
    cls.save_model("iris.mlmodel", format="coreml", export_parameters={'prediction_type': 'probability'})
  2. Import the resulting model to Xcode.

    The following is an example of importing with Swift:

    import CoreML
    let model = iris()
    let sepal_l = 7.0
    let sepal_w = 3.2
    let petal_l = 4.7
    let petal_w = 1.4
    guard let output = try? model.prediction(input: irisInput(feature_0: sepal_l, feature_1: sepal_w, feature_2: petal_l, feature_3: petal_w)) else {
    fatalError("Unexpected runtime error.")
    format: "Output probabilities: %1.5f; %1.5f; %1.5f",